mlpack: mlpack Documentation

Implementation of Continuous Mountain Car task. More...

Classes
struct	Action
	Implementation of action of Continuous Mountain Car. More...

class	State
	Implementation of state of Continuous Mountain Car. More...

Public Member Functions
	ContinuousMountainCar (const double positionMin=-1.2, const double positionMax=0.6, const double positionGoal=0.45, const double velocityMin=-0.07, const double velocityMax=0.07, const double duration=0.0015, const double doneReward=100, const size_t maxSteps=0)
	Construct a Continuous Mountain Car instance using the given constant. More...

State	InitialSample ()
	Initial position is randomly generated within [-0.6, -0.4]. More...

bool	IsTerminal (const State &state) const
	Whether given state is a terminal state. More...

size_t	MaxSteps () const
	Get the maximum number of steps allowed. More...

size_t &	MaxSteps ()
	Set the maximum number of steps allowed. More...

double	Sample (const State &state, const Action &action, State &nextState)
	Dynamics of Continuous Mountain Car. More...

double	Sample (const State &state, const Action &action)
	Dynamics of Continuous Mountain Car. More...

size_t	StepsPerformed () const
	Get the number of steps performed. More...

Detailed Description

Implementation of Continuous Mountain Car task.

Definition at line 29 of file continuous_mountain_car.hpp.

Constructor & Destructor Documentation

◆ ContinuousMountainCar()

ContinuousMountainCar	(	const double	positionMin = `-1.2`,
		const double	positionMax = `0.6`,
		const double	positionGoal = `0.45`,
		const double	velocityMin = `-0.07`,
		const double	velocityMax = `0.07`,
		const double	duration = `0.0015`,
		const double	doneReward = `100`,
		const size_t	maxSteps = `0`
	)

inline

Construct a Continuous Mountain Car instance using the given constant.

Parameters

positionMin	Minimum legal position.
positionMax	Maximum legal position.
positionGoal	Final target position.
velocityMin	Minimum legal velocity.
velocityMax	Maximum legal velocity.
duration	Time Duration for which force is applied on the car.
doneReward	Reward recieved by the agent on success.
maxSteps	The number of steps after which the episode terminates. If the value is 0, there is no limit.

Definition at line 105 of file continuous_mountain_car.hpp.

Member Function Documentation

◆ InitialSample()

State InitialSample ( )

inline

Initial position is randomly generated within [-0.6, -0.4].

Initial velocity is 0.

Returns: Initial state for each episode.

Definition at line 185 of file continuous_mountain_car.hpp.

References ContinuousMountainCar::State::Position(), mlpack::math::Random(), and ContinuousMountainCar::State::Velocity().

◆ IsTerminal()

bool IsTerminal ( const State & state ) const

inline

Whether given state is a terminal state.

Parameters

state desired state.

Returns: true if state is a terminal state, otherwise false.

Definition at line 200 of file continuous_mountain_car.hpp.

References Log::Info, and ContinuousMountainCar::State::Position().

Referenced by ContinuousMountainCar::Sample().

◆ MaxSteps() [1/2]

size_t MaxSteps ( ) const

inline

Get the maximum number of steps allowed.

Definition at line 220 of file continuous_mountain_car.hpp.

◆ MaxSteps() [2/2]

size_t& MaxSteps ( )

inline

Set the maximum number of steps allowed.

Definition at line 222 of file continuous_mountain_car.hpp.

◆ Sample() [1/2]

double Sample	(	const State &	state,
		const Action &	action,
		State &	nextState
	)

inline

Dynamics of Continuous Mountain Car.

Get reward and next state based on current state and current action.

Parameters

state	The current state.
action	The current action.
nextState	The next state.

Definition at line 132 of file continuous_mountain_car.hpp.

References ContinuousMountainCar::Action::action, mlpack::math::ClampRange(), ContinuousMountainCar::IsTerminal(), ContinuousMountainCar::State::Position(), and ContinuousMountainCar::State::Velocity().

Referenced by ContinuousMountainCar::Sample().

◆ Sample() [2/2]

double Sample	(	const State &	state,
		const Action &	action
	)

inline

Dynamics of Continuous Mountain Car.

Get reward based on current state and current action.

Parameters

state	The current state.
action	The current action.

Returns: reward, it's always -1.0.

Definition at line 173 of file continuous_mountain_car.hpp.

References ContinuousMountainCar::Sample().

◆ StepsPerformed()

size_t StepsPerformed ( ) const

inline

Get the number of steps performed.

Definition at line 217 of file continuous_mountain_car.hpp.

The documentation for this class was generated from the following file:

/home/ryan/src/mlpack.org/_src/mlpack-git/src/mlpack/methods/reinforcement_learning/environment/continuous_mountain_car.hpp